Security audit

Japan Media Agent

Security checks for vulnerabilities and agentic risk

Overview

This Japan-focused social media skill is mostly coherent, but it includes real public posting automation without clear confirmation or account-scoping safeguards.

Review carefully before installing if you may let agents access logged-in social accounts. Use it for drafting and strategy freely, but require a visible preview, exact destination account/platform, and your explicit approval immediately before any live post is made.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill explicitly describes automated posting to Pinterest, X, Instagram, and note via APIs or browser automation, but it does not require an explicit confirmation step or warn that account actions and content publication will occur on the user's behalf. In an agent context, this can lead to unintended posting, reputational damage, or misuse of authenticated sessions if the automation is triggered without clear user consent.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This markdown file explicitly defines the skill as a Japanese copywriting guide and presents Japanese as the default/only language. Under the language/locale policy, forcing a specific language without user opt-in can be a policy violation unless the locale restriction is clearly justified; the file does not state such an opt-in or limitation rationale.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The guideline '英語のみ（日本語必須）' requires Japanese as mandatory content language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified; this file is a Japan-focused guide, but it does not explicitly frame the language requirement as an optional or justified regional constraint for users.
Content: No source excerpt is available for this finding.